International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169

Volume: 5 Issue: 6 965 977

_______________________________________________________________________________________________

An Extended Review on Fabric Defects and Its Detection Techniques

2
M.Dhivya 1Dr.M.Renuka Devi,
1
Director, Department of MCA,
Sri venkateswara College of Computer Application and Management, Coimbatore.
2
Assistant Professor, Department of Computer Science,
VLB Janakiammal College of Arts & Science
Cum Research Scholar, Bharathiar University, Coimbatore.

Abstract: In Textile Industry, Quality of the Fabric is the main important factor. At the initial stage, it is very essential to identify and avoid the
fabrics faults/defects and hence human perception consumes lot of time and cost to reveal the fabrics faults. Now-a-days Automated Inspection
Systems are very useful to decrease the fault prediction time and gives best visualizing clarity- based on computer vision and image processing
techniques. This paper made an extended review about the quality parameters in the fiber-to-fabric process, fabrics defects detection
terminologies applied on major three clusters of fabric defects knitting, woven and sewing fabric defects. And this paper also explains about the
statistical performance measures which are used to analyze the defect detection process. Also, comparison among the methods proposed in the
field of fabric defect detection.

Keywords: Fabrics Defects; Fabric faults; Fabric defects terminology; Thresholding; fabric defect identification system
__________________________________________________*****_________________________________________________.

I. INTRODUCTION review on the all the methods which is applicable in all the
The textile industry is vertically-integrated across stages of fabric production process.
the value chain and extends from fiber to fabric to garments.
At the same time, it is a highly-fragmented sector, and
comprises small-scale, non-integrated spinning, weaving,
processing and cloth manufacturing enterprises.
Some of the Faults that commonly identified in the
fabric types are skewed or Bias, Back Fabric Seam
Impression ,Birdseye, Bowing ,Color Out, Color Smear,
Crease Mark, Crease Streak, Drop Stitches, Dye Streak In
Printing, End Out ,Jerk-in, Knots ,Missing Yarn ,Mixed End
(yarn) Mottled, Needle Line, Open Reed ,Pin ,Press-Off
, Printing Machine Stop ,Print Out of Repair ,Puckered
Selvage and Runner Sanforized Pucker Scrimp. The
purposes of visual inspection and decision making schemes
that are able to discriminate the features are extracted from
normal and defective regions. On the basis of nature of
features from the fabric surfaces, the proposed approaches
have been characterized into three categories: knitting,
woven and sewing defects.
These defects are occurred in any one of the stage of fabric
production process. The entire process of fabric production
is described in Figure-1. Any fault occurs in between this
flow of process will leads to faulty production result. So
keep track the entire process is the best way to deliver the
perfect material. While analyzing the fault prediction
method available in the context one should gives the deep

965

IJRITCC | June 2017, Available @ http://www.ijritcc.org

_______________________________________________________________________________________
International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
II. A REVIEW ON DEFECT DETECTION
METHODS IN KNITTED FABRICS
The author of the paper [1] attempts to present the first
survey on categorization of fabric defect detection
techniques in evaluating the qualities of identified features.
In order to evaluate the state-of-the-art, the limitations of
several promising techniques are identified and
performances are analyzed. In paper [2], the author
proposed a gray level co-occurrence that can be specified in
a matrix of the relative frequencies with which two
neighboring pixels separated by a distance occur on the
image. By applying the co-occurrence matrix and gray
relational analysis of the gray theory, we can extract
characteristic values of a fabric defect image and classify
defects to recognize common problems, including broken
warps, broken wefts, holes, and oil stains. Gray relational
analysis is also used to investigate correlations of the
analyzed factors among the selected characteristic indicators
in a randomized factor sequence through data processing. In
paper[3], fabric defects have been detected and classified
from a video recording captured during the quality control
process. The defective areas on the fabric surface were
detected using the heat difference occurring between the
defective and defect-free zones. Gray level co-occurrence
matrix is used for feature extraction for defective images.
The defective images are classified by k-nearest neighbor
algorithm. The image processing stage consists of wavelet,
threshold, and morphological operations.
In paper [4] the author addresses issues concerning image
analysis algorithms for the visual quality inspection of
textile fabrics. An overview of a number of flaw detection
techniques and analysis of their suitability for detecting the
presence of weaving defects is presented. The flaw detection
algorithms are based on a local analysis of spatial and
spatial-frequency domain features, exploring both the
statistical and structural texture analysis of the defective
image samples. The methods that are applied to the flaw
detection problem are spatial grey level co-occurrence;
normalized cross-correlation; texture blob detection; and
spectral approaches. The relations between energy and the
local binary pattern as a new concept called energy-based
local binary patterns (ELBPs) are defined by the author in
paper[5]. The defects can be detected, using ELBPs rather
than grayscale-based local binary patterns. The proposed
method can detect chromatic and structural defects.
The author introduce an efficient algorithm in paper[6],
which combines concepts from wavelet theory and co-
occurrence matrices for detection of defects encountered in
textile images. Detection of defects within the inspected
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
texture is performed first by decomposing the gray level
images into sub-bands, then by partitioning the textured
image into non-overlapping sub windows and extracting the
co-occurrence features and finally by classifying each sub-
window as defective or non-defective with a Mahalanobis
distance classifier being trained on defect free samples a
priori. There arises a problem of automated defect detection
in textured materials is investigated. The author introduces a
new approach for defect detection using linear FIR filters
with optimized energy separation is proposed. The issues
relating to the design of optimal filters for supervised and
unsupervised web inspection are addressed. A general web
inspection system based on the optimal filters is proposed.
The low computational requirement confirms the usefulness
of the approach for industrial inspection. The author in
paper [7] proposed a real time fabric defect detection system
(FDDS), implemented on an embedded DSP platform.
Textural features of fabric image are extracted based on gray
level co-occurrence matrix (GLCM). A sliding window
technique is used for defect detection where window moves
over the whole image computing a textural energy from the
GLCM of the fabric image. The implementation is carried
out on a TI TMS320DM642 platform and programmed
using code composer studio software. The authors presented
a multi-resolution approach for the inspection of local
defects embedded in homogeneously textured surfaces in
paper [8]. It is based on an efficient image restoration
scheme using the wavelet transforms. By properly selecting
the smooth sub-image or the combination of detail sub-
images at different resolution levels for image
reconstruction, the global repetitive texture pattern can be
effectively removed and only local anomalies are preserved
in the restored image. A wavelet band selection procedure is
developed to automatically determine the best
reconstruction parameters based on the energy distribution
of wavelet coefficients. The defects in a variety of real
textures including machined surfaces, natural wood, sand
paper and textile fabrics are well detected.
Comparison of six wavelet transform-based classification
methods are compared in paper [9], using different
discriminative training approaches to the design of the
feature extractor and classifier are compared. These six
classification methods are: methods of using an Euclidean
distance classifier and a neural network classifier trained by
maximum likelihood method and back propagation
algorithm, respectively; methods of using an Euclidean
distance classifier and a neural network classifier trained by
minimum classification error method, respectively; method
of using a linear transformation matrix-based feature
extractor and an Euclidean distance classifier, designed by
discriminative feature extraction (DFE) method; method of
966
International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
using an adaptive wavelet-based feature extractor and an
Euclidean distance classifier, designed by the DFE method.
In paper [10] the author presents a novel approach for defect
detection of fabric textile. For this purpose, all wavelet
coefficients were extracted from the perfect fabric. These
coefficients can delete main fabric of image and indicate
defects of fabric textile and so the authors were using the
Genetic Algorithm for finding a suitable subset. The
evaluation function in GA was Shannon entropy. Finally, it
was shown that we can gain better results for defect
detection, by using two separable sets of wavelet
coefficients for horizontal and vertical defects. This
approach, not only increases accuracy of fabric defect
detection, but also, decreases computation time. A simulated
fabric model is used by author in paper [11] to understand
the relationship between the fabric structure in the image
space and in the frequency space. Based on the three-
dimensional frequency spectrum, two significant spectral
diagrams are defined and used for analyzing the fabric
defect. The author in paper [12] introduces a global
approach for automatic inspection of defects in randomly
textured surfaces like sandpaper, castings, leather, and many
industrial materials. The proposed method is based on a
global image reconstruction scheme using the Fourier
transform (FT) but does not rely on local features of the
textures. Since a statistical texture has the surface of random
pattern, the spread of frequency components in the power
spectrum space is isotropic. The author makes use of inverse
FT to remove the periodic, repetitive patterns of any
statistical textures.
A new method for fabric defect detection by incorporating
the design of an adaptive wavelet-based feature extractor
with the design of an Euclidean distance-based detector is
introduced by the author in paper [13]. The proposed
method characterizes the fabric image with multiscale
wavelet features by using undecimated discrete wavelet
transforms. Each non overlapping window of the fabric
image is then detected as defect or non defect with an
Euclidean distance-based detector. An adaptive wavelet
basis is designed for the detection of fabric defects instead
of using the standard wavelet. Minimization of the detection
error is achieved by incorporating the design of the adaptive
wavelet with the design of the detector parameters using a
discriminative feature extraction (DFE) training method. In
paper [14], the author extends the adaptive wavelet-based
methodology from the use of a single adaptive wavelet to
multiple adaptive wavelets. Defect-specific adaptive wavelet
was designed to enhance the defect region at one channel of
the wavelet transform, where the defect region can be
detected by using a simple threshold classifier.
Corresponding to the multiple defect-specific adaptive
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
wavelets, the multi-scale edge responses to defect regions
have been shown to be more efficient in characterising
defects, which leads to a new approach to the classification
of defects.
The authors introduced an ultrasonic method in paper [15]
and system are provided for monitoring a fabric to identify a
defect. A plurality of ultrasonic transmitters generate
ultrasonic waves relative to the fabric. An ultrasonic
receiver means responsive to the generated ultrasonic waves
from the transmitters receives ultrasonic waves coupled
through the fabric and generates a signal. The digitized
signal is processed to identify a defect in the fabric. The
digitized signal processing includes a median value filtering
step to filter out high frequency noise. Then a mean value
and standard deviation of the median value filtered signal is
calculated. The calculated mean value and standard
deviation are compared with predetermined threshold values
to identify a defect in the fabric. The authors in paper[16]
proposed a novel defect detection scheme for fabric
inspection based on bi-dimensional empirical mode
decomposition. The stopping criterion for sifting and the
intrinsic mode functions (IMFs) are adapted for this specific
application. Appropriate IMFs are selected to eliminate
influences of fabric textures and lighting in defect
segmentation. The proposed method is a robust and accurate
approach for fabric defect inspection. A pilot system for
defect detection and classification of web textile fabric in
real-time are introduced by the author in paper [17]. The
general hardware and software platform, developed for
solving this problem, is presented while a powerful novel
method for defect detection after multi resolution
decomposition of the fabric images is proposed. An artificial
neural network, trained by a back-propagation algorithm,
performs the defect classification in categories.
In paper [18], the authors introduce an intelligent color-
textured fabric defect detection and classification model
using genetic algorithms and the Elman neural network. A
color ring projection is used for image processing, and the
solution for optimization of parameters is based on the
genetic algorithm method. The new modified Elman
network is proposed which is more feasible to classify the
type of fabric defects, which have proportional, integral, and
derivative properties. The authors proposed an approach of
using local contrast deviation (LCD) based on the
characteristics of fabric structure in paper [19] for fabric
defect detection. LCD is a parameter used to describe
features of the contrast difference in four directions between
the analyzed image and a defect-free image of the same
fabric, and is used with a bi level threshold function for
defect segmentation. The validation tests on the developed
algorithms were performed with fabric images from
967
International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
TILDAs Textile Texture Database and captured by a line-
scan camera on an inspection machine. In paper[20], the
authors presented a new defect detection algorithm for
textured images where proposed by the author in paper [20]
based on the sub-band decomposition of gray level images
through wavelet filters and extraction of the co-occurrence
features from the sub-band images. Detection of defects
within the inspected texture is performed by partitioning the
textured image into non-overlapping sub-windows and
classifying each sub-window as defective or non-defective
with a mahalanobis distance classifier being trained on
defect free samples a priori.
The author in paper [21] describes a computer vision-based
fabric inspection system implemented on a circular knitting
machine to inspect the fabric under construction. The first
part is the detection of defects in knitted fabric was
performed and the performance of three different spectral
methods, namely the discrete Fourier transform, the wavelet
and the Gabor transforms were evaluated off-line. The
second part is the knitted fabric defect-detection and
classification was implemented on-line. The captured
images were subjected to a defect-detection algorithm,
which was based on the concepts of the Gabor wavelet
transform, and a neural network (as a classifier). The fabric
images were broadly classified into seven main categories as
well as seven combined defects. A new method is proposed
by author in paper [22] for knitted fabric defect detection
and classification using image analysis and neural networks.
Images of six different induced defects were obtained and
used in the analysis. Statistical procedures and Fourier
Transforms were utilized as two different approaches in the
feature extraction effort and neural networks were used to
detect and classify the defects. The study [23] has shown
that image analysis has great potential to provide reliable
measurements for detecting defects in knitted fabrics. An
automatic fabric evaluation system, which enables automatic
computerized defect detection (analysis of knitted fabrics)
was developed. This analysis system is capable of on-line
detection of fabric defects and full control in the knitting
machine by the way of stopping the circular knitting
machine as soon as a defect is acquired by the digital
camera. The author introduces a new approach in paper [24]
for classification of circular knitted fabric defect is proposed
which is based on accepting uncertainty in labels of the
learning data. There are some classification problems in
which a considerable amount of uncertainty exists in the
labels of samples. The main core of this research has been
usage of the uncertain information of labeling and their
combination with the DempsterShafer theory of evidence.
In paper [25], the authors introduce the system which
combines the fuzzification technique with fuzzy logic and a
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
back-propagation learning algorithm with neural networks.
Four input featuresthe ratio of projection lengths in the
horizontal and vertical directions, the gray-level mean and
standard deviation of the image, and the large number
emphasis (LNE) based on the neighboring gray level
dependence matrix for the defect areaare selected and
their usefulness is justified. The neural network is also
implemented and compared with the neural-fuzzy system.
A new approach for fabric defect classification using radial
basis function (RBF) network improved by Gaussian
mixture model (GMM) is investigated by the author in study
[26]. First, the gray level arrangement in the neighborhood
of each pixel is extracted as the feature. This raw feature is
subject to principal component analysis (PCA) which adopts
the between class scatter matrix as the generation matrix to
eliminate the variance within the same class. Second, the
RBF network with Gaussian kernel is used as the classifier
because of the nonlinear discrimination ability and support
for multi-output. A novel method for texture defect
detection is presented in paper [27], there this method makes
use of Independent Component Analysis (ICA) for feature
extraction from the non-overlapping sub-windows of texture
images and classifies a sub-window as defective or non-
defective according to Euclidean distance between the
feature obtained from average value of the features of a
defect free sample and the feature obtained from one sub-
window of a test image. The authors proposed a new
approach in paper[28] for the segmentation of local textile
defects using feed-forward neural network. Every fabric
defect alters the gray-level arrangement of neighboring
pixels, and this change is used to segment the defects.
Principal component analysis using singular value
decomposition is used to reduce the dimension of feature
vectors. The acceptance of a visual inspection system
depends on economical aspects as well. Therefore, a new
low-cost solution for the fast web inspection using linear
neural network is also presented.
III. A REVIEW ON DEFECT DETECTION
METHODS IN WOVEN FABRICS
A new algorithm based on multichannel filtering is
presented in paper [29]. The texture features are extracted
by filtering the acquired image using a filter bank consisting
of a number of real Gabor functions, with multiple narrow
spatial frequency and orientation channels. For each image,
the authors propose the use of image fusion to multiplex the
information from sixteen different channels obtained in four
orientations. This algorithm realizes large computational
savings over the previous approaches and enables high
quality real-time defect detection. In study [30], a new
method based on the use of thermal camera for detecting
968
International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
these defects from the textile fabric images is presented. For
identification process of defective area, fabric images were
obtained by a thermal camera during the fabric flow in
quality control machine that was specially designed for this
experiment. Defective and defect-free regions on fabric
surface were determined by thermal camera due to the
thermal differences. The mentioned thermal defect detection
system will eliminate the worker usage for fabric quality
control process, thus it will provide a cost-effective and
competitive manufacturing. A novel defect detection scheme
based on morphological filters is proposed by the author to
tackle the problem of automated defect detection for woven
fabrics in paper [31]. In that scheme, important texture
features of the textile fabric are extracted using a pre-trained
Gabor wavelet network. These texture features are then used
to facilitate the construction of structuring elements in
subsequent morphological processing to remove the fabric
background and isolate the defects.
The author presents a new scheme in paper [32] for
automated FDDS implementation using GLCM and also
compares it with Gabor filter approach. GLCM texture
statistics are extracted and plotted against the inter-pixel
distance of GLCM as signal graph. The non-defective fabric
image information is compared with the test fabric image. In
Gabor filter based approach, a bank of Gabor filter with
different scales and orientations is generated and fabric
images are filtered with convolution mask. In paper [33], the
author investigated the problem of automated defect
detection in textured materials. The authors introduce a new
approach for defect detection using linear FIR filters with
optimized energy separation is proposed. Performance of
different feature separation criterion with reference to fabric
defects has been evaluated. The issues relating to the design
of optimal filters for supervised and unsupervised web
inspection are addressed. A general web inspection system
based on the optimal filters is proposed. The paper [34],
explains the investigation of the problem of automated
defect detection for textile fabrics and proposes a new
optimal morphological filter design method for solving this
problem. Gabor Wavelet Network (GWN) is adopted as a
major technique to extract the texture features of textile
fabrics. An optimal morphological filter can be constructed
based on the texture features extracted. In view of this
optimal filter, a new semi-supervised segmentation
algorithm was then proposed.
A fabric defect detection method based on Gabor filter
masks is proposed in paper [35] on one even symmetric
Gabor filter mask and one odd symmetric Gabor filter mask
derived from the impulse response of the optimal Gabor
filter are used. The optimal Gabor filter is designed to match
with the texture features of defect-free fabric image, whose
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
parameters are obtained by using the genetic algorithm. The
author investigates the problem of automatic and robust
fabric defect detection and classification which are more
essential and important in assuring the fabric quality in
paper [36]. Two characteristics of this work are: a new
scheme combining Gabor filters and Gaussian mixture
model (GMM) is proposed for fabric defect detection and
classification , the test data is actually collected from
Qinfeng textile factory, China, including nine different
fabric defects with more than 1000 samples. The author
aims at investigating methods in paper [37] for solving the
problem of automated fabric defect detection and
classification, which are more essential and important in
assuring the fabric quality. The author focuses the work on
two aspects: fabric defect detection and classification. First
the detection texture features for texture defect are extracted
using Gabor filters. The method would automatically
segment defects from the regular texture. Second, texture
features for classification use local binary patterns and
Tamura method.
In paper [38], the author carries an extensive evaluation on
the performance of a generalized motif-based method for
detecting defects .The motif-based method evolves from the
concept that every wallpaper group is defined by a lattice,
which contains a further constituent motif. Decision
boundaries are determined by learning the distribution of
those values among the defect-free and defective patterns in
the energy-variance space. The authors presented a novel
approach in paper [39] to the fast detection and extraction of
fabric defects from the images of textile fabric. Automated
visual inspection systems are much needed in the textile
industry, especially when the quality control of products in
textile industry is a significant problem. For the detection of
fabric defects, we first decompose the image into its bit
planes. The lower order bit planes are found to carry
important information of the location and shape of defects.
A method of detecting the fabric defects automatically based
on Gabor filters is introduced in paper [40]. The proposed
method is based on the energy response from the
convolution of Gabor filter banks in different frequency and
orientation domains. Using the image fusion to combine all
response feature images and finally the threshold of this
fused image produces a simple binary image of defects. The
authors in paper [41] proposed a method of fabric defect
detection online based on Gabor filter bank is proposed.
First, optimal Gabor filter bank is designed to match texture
features of normal fabric image and built adopting the half-
peak tangent method. The fabric defect image is treated
using this filter bank, and filtered sub-images are obtained
which characterize the fabric defect in different orientations
and frequencies. Finally, these sub-images are fused to
969
International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
reconstruct a binary defect image. And the binary defect
image is output to finish the detection.
The theoretical basis of a technique is presented in paper
[42] for real time defect detection in fabrics using a joint
transform correlator. This correlation technique is an
extension of Fourier transform analysis and is extremely
useful for real time pattern recognition. The regular periodic
nature of a woven fabric makes it possible to use the Fourier
transform technique to detect defects.. Cross- and auto-
correlation peaks, generated after the execution of the
second Fourier transform on the filtered joint power
spectrum, indicate the existence of a particular defect type.
A fractional power fringe adjusted filter is used for efficient
detection of defects. The author introduces a simulated
fabric model in paper [43] which is used to understand the
relationship between the fabric structure in the image space
and in the frequency space. The author uses two significant
spectral diagrams called the central spatial frequency
spectrums which is mainly used for analyzing the fabric
defect. The fabric defects are broadly classified into four
classes: 1) double yarn; 2) missing yarn; 3) webs or broken
fabric; and 4) yarn densities variation. After evaluating these
four classes of defects using some simulated models and real
samples, seven characteristic parameters for a central spatial
frequency spectrum are extracted for defect classification. In
paper [44], the method of wavelet preprocessed golden
image subtraction (WGIS) has been developed for defect
detection on patterned fabric or repetitive patterned texture.
This paper also presents a comparison of the three methods.
The author presents a new method in study [45] to capture
the texture information using adaptive wavelet bases.
Wavelets are compact functions which can be used to
generate a multi resolution analysis. Texture constraints are
used to adapt the wavelets to better characterize specific
textures. This paper demonstrates how adaptive wavelet
basis can be used to locate defects in woven fabrics. A
wavelet-filter method that minimizes entropy in the wavelet
transform of images of woven fabrics is designed in paper
[46]. Filters that minimize entropy in images tend to filter
out fabric texture while highlighting fabric defects. The
design of the wavelet filter is couched as a non-convex
optimization problem which is solved using a hybridized
Genetic Algorithm. Three distinct filters are tuned to detect
horizontal, vertical and blob defects in woven fabrics. In
addition to texture filtering, defect segmentation, noise
removal, and object extraction are presented.
The author introduced a vision-based online fabric
inspection methodology in study [47] for woven textile
fabrics. The proposed inspection system consists of
hardware components consist of CCD array cameras, a
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
frame grabber and appropriate illumination and software
components routines capitalize upon vertical and horizontal
scanning algorithms to reduce the 2-D image into a stream
of 1-D data. The wavelet transform is used next to extract
features that are characteristic of a particular defect. The
defect declaration is carried out by employing SNRs and
scanning methods. Learning routines are called upon to
optimize the wavelet coefficients. In paper [48], the authors
introduce a prototype system for automatic in-line flaw
detection in industrial woven fabrics. The authors describe
the process flow to segment single yarns in high-resolved (
1000 ppi) textile images. This work is partitioned into two
parts: First, mechanics, machine integration, vibration
cancelling and illumination scenarios are discussed based on
the integration into a real loom. Subsequently, the software
framework for high precision fabric defect detection is
presented. A new method based on using features is
proposed for defect detection in paper [49] for patterned
fabrics. In the training stage, at first step LBP operator is
applied to an image of defect free fabric, pixel by pixel, and
the reference feature vector is computed. Then this image is
divided into windows and LBP operator is applied to each of
these windows. In the detection stage, a test image is
divided into windows and using the threshold, defective
windows can be detected. The authors discussed computer-
vision-based automatic detection of fabric defects in paper
[50] which is one of the difficult one-class classification
tasks in the real world. To overcome the incapacity of a
single fractal feature in dealing with this task, multiple
fractal features have been extracted in the light of the theory
of and problems present in the box-counting method as well
as the inherent characteristics of woven fabrics. A robust
new scheme is presented in this paper for optimally
selecting values of the parameters especially that of the scale
parameter of the Gaussian kernel function involved in the
training of the SVDD model.
IV. A REVIEW ON DEFECT DETECTION
METHODS IN SEWING FABRICS
The author presents the theoretical foundation of the method
in paper[51] and defines the relations between motifs and
lattice, from which a new concept called energy of moving
subtraction is derived using norm metric measurement
between a collection of circular shift matrices of motif and
itself. A fast normalized cross correlation computation for
defect detection application in paper [52] is proposed by
author. Given larger images of size M N and the
neighbourhood window of size m n , the computational
complexity can be significantly reduced from O(m n M
N) with the traditional normalized correlation operation to
only O(M N) with the proposed sum-table scheme. In
970
International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
paper [53], the author presents a study of using ellipsoidal
decision regions for motif-based patterned fabric defect
detection to improve the original detection success using
maxmin decision region of the energy-variance values. In
our previous research, maxmin decision region was found
to be effective in distinct cases but ill detect the ambiguous
false-positive and false-negative cases. To alleviate this
problem, we first assume that the energy-variance values
can be described by a Gaussian mixture model. Second, we
apply k-means clustering to roughly identify the various
clusters that make up the entire data population. Third,
convex hull of each cluster is employed as a basis for fitting
an ellipsoidal decision region over it. Defect detection is
then based on these ellipsoidal regions.
The adaptive wavelet design for fabric defect detection is
used in paper[54] to achieve translation invariance and more
flexible design. The authors design the wavelet filters under
the constraints that the analysis filters are power
complementary, and the wavelet has one vanishing moment,
which corresponds to a multi-scale edge detector. Adaptive
wavelets are designed for five kinds of fabric defects in the
experiments. Comparing the proposed method with adaptive
wavelet design for defect detection based on orthogonal
wavelet transform, the author design has largely improve the
ratio of wavelet transform energy between the defect area
and the background. The authors introduce a visual
inspection methods in paper [55] for defect detection on
patterned fabrics. A review on some defect detection
methods on patterned fabrics will be given. Then, a new
method for patterned fabric inspection called Golden Image
Subtraction (GIS) is introduced. GIS is an efficient and fast
method, which can segment out the defective regions on
patterned fabric effectively. An improved version of the GIS
method using wavelet transform is also given. To develop
an automated visual inspection method for defect detection
on patterned fabric the author uses the wavelet transform in
his study [56]. The authors introduce methods like direct
thresholding (DT) based on WT detailed sub-images and the
golden image subtraction method (GIS). GIS is an efficient
and fast method, which can segment out the defective
regions on patterned fabric effectively.
In study [57], the authors introduce a new technique called
fractal scanning, is developed to scan the digitized image of
textile fabrics. A fuzzificd wavelet transform algorithm with
adaptive noise rejection and on-line learning is used to
extract features and a knowledge based inference engine is
called upon to declare the defect categories. Off-line
learning is introduced to maximize the detachability and
identifiability measures. The authors introduce a new
method that combines the concepts of wavelet
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
transformation and Independent Component Analysis (ICA)
in paper [58] for defect detection problem in textile images.
The authors aim is to find the independent components of
the wavelet transform of textile fabric images for the
purpose of defect detection. In paper [59], the authors
introduce a stitching detection and classification technique,
which combines the improved thresholding method based on
the wavelet transform with the back propagation (BP) neural
network. The author uses the direct thresholding method,
which is based on wavelet transform smooth subimages
from the use of a quadrant mean filtering method, to
attenuate the texture background and preserve the
anomalies. The images are then segmented by thresholding
processing and noise filtering. Nine characteristic variables
based on the spectral measure of the binary images were
collected and input into a BP neural network to classify the
sample images.
An implemention of a textile defect detector which uses
computer vision methodology is done by the author in paper
[60] with the combination of multi-layer neural networks to
identify the classification of textile defects and detect it with
a real time configured mechanical system containing a
microcontroller. The recognizer, suitable for LDC countries,
especially for Bangladesh where textile exports earns the
maximum for the countrys economy. In paper [61], the
authors introduce a defect detection system which includes a
video camera with defect detection circuits for detecting
defects in video signals being outputted by corresponding
sections of an array sensor such as a TDI CCD two-
dimensional array sensor. Each defect detection circuit
includes a subtraction circuit for subtracting a prior stored
pixel from an incoming pixel to generate a difference. The
prior stored pixel is updated to the succeeding pixel only
when the difference value is acceptable. The memories are
sequentially read up to their end of line bits, and the defect
pixel values along with coordinates expanded to include
section indicating bits are transferred from the camera to
further processing facilities. The author in paper [62] uses
the multiple line scan cameras and multiple computers for
preprocessing and post processing provides detailed
analysis. This system does not identify the specific defect or
cause, but does save a picture of a portion of the defect
which can be reviewed by an operator or quality assurance
technician. The system is described and the defect
detection/identification algorithms discussed.
A fabric defect detecting system in paper [63] that uses an
advanced method involving computer vision and image
analysis is capable of defect classification. Image pre-
processing techniques that enhance raw images are applied
before defect classification by a K-means algorithm and
971
International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
statistical method. These generate a Bayes classifier from
which a decision surface is created for a classification
procedure that can categorize defective or non-defective
regions. The advantages of using the decision surface are a
reduction in the training step and the ability to rapidly
classify fabric. The author introduces a fabric detect
detection scheme in study [64] based on HOG and SVM is
proposed. Histograms of orientated gradients (HOG) where
the feature of the image is encoded and it is insensitive to
various lightings and noises. The powerful feature selection
algorithm, AdaBoost, is performed to automatically select a
small set of discriminative HOG features in order to achieve
robust detection results. In the end, support vector machine
(SVM) is used to classify the fabric defects. A new approach
to the problem of textile surface quality evaluation is
presented in paper [65]. This new approach is based on the
capture and analysis of the profile of protrusions. The
specific methods of image processing for protrusion
detection and parameterization have been elaborated. New
algorithms for the grading of four types of fabric defect
pilling, fuzziness, snagging, and hairiness which can be used
to demonstrate a high level of coincidence between the
obtained grades of all types of defect with expert grades.
V. QUANTITATIVE COMPARISON AND
DISCUSSION
A quantitative comparison between the various defect
detection in knitting, woven and sewing fabrics are surveyed
in this paper. The performance of each methods applied to
detect the defect in those types of fabrics have been
assessed/reported on the fabric test images with varying
resolution, background texture and defects is very difficult.
Higher computational complexity can be justified with
better performance on high resolution images but this also
may not always hold good in various applications and
overall cost of system. Some of approaches developed in
[28], [6], [66], [67] have been in evaluated on image sample
with various resolutions. The resolution of the images used
for the detection process also matters a lot. Different
techniques use different dataset of information. While
examining on those techniques, Regular Band based
Methodology is used to detect small defects with box, star or
dot patterns. FDDS implemented on a Texas Instruments
TMS320DM642 Evaluation Module, process one frame at a
time. Moving window analysis is performed on each frame
and the defects are marked with white squares on the input
fabric image.
The high resolution images are highly suitable for detecting
defects with very subtle intensity variations, but their use
will require a high volume of online computations for
unsupervised defect detection. Ozdemir et al. compared six
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
texture features, consisting of MRF, KL transform, 2D
lattice filters, Laws filters, Co-occurrence matrices, and a
FFT - based method, for detecting textile defects. Also, by
considering the results obtained with respect to speed and
reliability, MRF approach seems feasible for a real-time
factory implementation. Also Bodnarova et al. [68] have
concluded that the optimal Gabor filters (optimized to detect
five types of defects) perform better than gray level co-
occurrence matrix, correlation or FFT based approaches.
Lee Tin Chi [69], compares the performance of three
methods which utilize matched masks, wavelet transform
and neural network for fabric defect detection. The wavelet
transform method was the least effective, because it was
only able to detect effectively certain classes of fabric
defects. Comparative studies performed by Randen et.al.
[70, 71] and Chen et al. [72] indicate that the Gabor features
in most of the cases outperform the other methods regarding
the complexity and overall error rate. The online defect
inspection system of mesh fabric was established by
integrating the motor, encoder, linear CCD camera, capture
card, industrial computer, converter, light source, and
inspection system software. These operations took various
duration for each steps. Some of authors have proposed
improved systems with high real-time performance.
The performance are evaluated by visually assessing the
quality of the binary output images. True detections (TP) are
recorded when (1) the white areas of the binary output
image only overlap the areas of the corresponding defects in
the fabric image, and (2) no white area appears in the binary
output image if the fabric image contains no defect. False
alarms (FP) are recorded when the white areas appearing in
the binary output image do not only overlap the areas of the
corresponding defects in the fabric image, but also appear in
some other areas significantly distant from the defect areas,
or when white areas appear in the binary output image when
the fabric image contains no defect. Overall detection (OD)
is the sum of TP and FP. Missed detection (FD), which is
the sum of True Negative (TN) and False Negative (FN)
means that no white area appears in the binary output image
even if the fabric image contains a defect. The Figure-2
confusion matrix is based on the above metrics and
statistical performance measures are derived.
972
International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169
Volume: 5 Issue: 6 965 977
_______________________________________________________________________________________________
Condition
Condition
Condition Positive
Negative
Test
False Positive(FP)
Outcome True Positive(TP)
(Type I error)
Test Positive
Outcome Test
False Negative(FN)
Outcome True Negative(TN)
(Type II error)
Negative

Figure 2: Confusion Matrix for Detection Performance Analysis

The Figure-3 explains the analysis of few methods and its examined defects based on the review papers.

Figure 3: Graphical analysis of few methods and its examined defects

The equation listed in Table-1 is used to calculate the
performance measure of the fabric detection system
statistically. These statistical measures may be used to plot
the results graphically and to evaluate the system and
compression with other state-of-art systems. In Table-2 the
detailed explanation about the publication, methods applied
on it, which type of defects are experimented or identified
and derived grading efficiency are given.

S. No Performance Measure Formula

TP
1 Sensitivity
TP FN
TN
2 Specificity
FP TN
TP
3 Precision
TP FP

973

IJRITCC | June 2017, Available @ http://www.ijritcc.org

_______________________________________________________________________________________
International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169
Volume: 5 Issue: 6 965 977
_______________________________________________________________________________________________
TP
4 Recall
TP FN
Pr ecision . Re call
5 F-Score 2*
Pr ecision Re call

Table 1 Statistical Formula for Defect Detection Performance Analysis

Grading
S.
Title & Year of Publication Methods Applied Defects Experimented Efficienc
No
y
Automated Fabric fault
detection using Morpho Bitplane decomposition &
1 Woven fabric defects 93.2%
logical operation on Bit Weighted morphology
plane,2015[73]
Novel image
Automated patterned fabric Envision defective objects in
2 Decomposition method 95%
fault detection ,2015 patterned fabric image
ANN classifier
machine faults, hole, Color
Fabric fault processing using
bleed, problems ,scratch poor
3 image processing Histrogram, Thresholding 86%
finishing ,dirt spot, excessive
Techniques,2015[74]
stretching ,crack point
Automated patterned fabric Histrogram,
4 Patterned Fabric Defects 95%
fault detection, 2015[75] Thresholding,Gray Scale
Evaluation of yarn quality in IP-Mathematical
5 Thickness of yarn 85%
fabric, 2014 (Stat)Model
Hole,stain,miss-pick,miss-
Defect detection in fabric
end,double-pick,double- D >=20-
6 images using SVD SVD Technique
end,weft-float,wrap- Defects
techniques,2014[76]
float,course-pick,course-end
Fabric Fault processing Hole,Sctrach,Fading,Broken
7 perfections & Histrogram, Thresholding ends,broken 85%
imperfection,2014[77] picks,float,gout,cut
Texture defect detection using DCT/H-image method, 96.01 to
8 Local Homo -geneity & Multivariate statistics
Common fabric defects
DCT,2014[78] method 97.8%
Yarn parameterization & Artificial intelligence Yarn faults-thin & thick
9 90%
fabric prediction 2013[79] Method places &neps
Measuring the roughness of
10 knitted fabrics by analysis of Kawabata Method Knitted fabric roughness 88%
surface signals 2013[80]
Fabric fault processing using Global thresholding &
Broken ends,broken
11 image processing technique Local or Adaptive 85%
picks,float,gout,hole,cut
2013[81] Thresholding
Fabric defect detection based
12 on GLCM & Gabour filter GLCM & Gabour filter Blob shaped,edge shaped 94%
2013[82]
13 Real Time fabric defect GLCM Texture defect 88%
974

IJRITCC | June 2017, Available @ http://www.ijritcc.org

_______________________________________________________________________________________
 International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169
Volume: 5 Issue: 6 965 977
_______________________________________________________________________________________________
detection system on
Embedded DSP
platform,2013
Determination of diameter
Artificial Intelligence Neps identification in
14 spectrogram & Neps for yarn 87%
Method yarn(Cotton &jute)
parameterization, 2013[83]

Table 2 Tabular analysis of few methods and its examined defects.

VI. CONCLUSION [10] Heidari, N., Azmi, R., & Pishgoo, B. (2011). Fabric textile
In this paper, major defect detection techniques are surveyed defect detection, by selecting a suitable subset of wavelet
based on three fabric defects namely knitting, woven and coefficients, through genetic algorithm. International
Journal of Image Processing (IJIP), 5(1), 25.
sewing fabrics. According to this survey we found that the
[11] 11.. Chan, C. H., & Pang, G. K. (2000). Fabric defect
system is fully automatic as well as defect is detected in all
detection by Fourier analysis. Industry Applications, IEEE
sort of steps in fabric production process is needed. The Transactions on, 36(5), 1267-1276.
application methodology opted for each fabric type is [12] Tsai, D. M., & Huang, T. Y. (2003). Automated surface
dissimilar to one another. We hope that this paper would be inspection for statistical textures. Image and Vision
useful for every newcomer to the area of automated fabric computing, 21(4), 307-323.
defect inspection. The comprehensive survey presented in [13] Yang, X. Z., Pang, G. K., & Yung, N. H. (2002).
this paper will be useful to develop and analyze a novel Discriminative fabric defect detection using adaptive
approach. wavelets. Optical Engineering, 41(12), 3116-3126.
[14] Yang, X., Pang, G., & Yung, N. (2005, December). Robust
fabric defect detection and classification using multiple
REFERENCE
adaptive wavelets. In Vision, Image and Signal Processing,
[1] Kumar, A. (2008). Computer-vision-based fabric defect
IEE Proceedings- (Vol. 152, No. 6, pp. 715-723). IET.
detection: a survey. Industrial Electronics, IEEE
[15] Sheen, S. H., Chien, H. T., Lawrence, W. P., & Raptis, A. C.
Transactions on, 55(1), 348-363.
(1997). U.S. Patent No. 5,665,907. Washington, DC: U.S.
[2] Kuo, C. F. J., & Su, T. L. (2003). Gray relational analysis
Patent and Trademark Office.
for recognizing fabric defects. Textile Research
[16] Li, Z., Liu, J., Liu, J., & Gao, W. (2014). Fabric defect
Journal, 73(5), 461-465.
segmentation by bidimensional empirical mode
[3] Yldz, Kazm, Ali Buldu, and Mustafa Demetgul. "A
decomposition. Textile Research Journal,84(7), 704-713.
thermal-based defect classification method in textile fabrics
[17] 17.. Karayiannis, Y.A., Stojanovic, R., Mitropoulos, P.,
with K-nearest neighbor algorithm."Journal of Industrial
Koulamas, C., Stouraitis, T., Koubias, S., Papadopoulos, G.,
Textiles (2014): 1528083714555777.
Defect detection and classification on web textile fabric
[4] Wen, Z., Cao, J., Liu, X., & Ying, S. (2014). Fabric defects
using multiresolution decomposition and neural networks,
detection using adaptive wavelets. International Journal of
Proceedings of 6th IEEE International Conference on
Clothing Science and Technology,26(3), 202-211.
Electronics, Circuits and Systems, 5-8 Sep 1999, pp.765-768.
[5] Li, W., Xue, W., & Cheng, L. (2012). Intelligent detection of
[18] Zhang, Y. H., Yuen, C. W. M., Wong, W. K., & Kan, C. W.
defects of yarn-dyed fabrics by energy-based local binary
(2011). An intelligent model for detecting and classifying
patterns. Textile Research Journal, 82(19), 1960-1972.
color-textured fabric defects using genetic algorithms and the
[6] Latif-Amet, A., Ertzn, A., & Eril, A. (2000). An efficient
Elman neural network. Textile Research Journal, 81(17),
method for texture defect detection: sub-band domain co-
1772-1787.
occurrence matrices. Image and Vision computing, 18(6),
[19] Shi, M., Fu, R., Guo, Y., Bai, S., & Xu, B. (2011). Fabric
543-553.
defect detection using local contrast deviations. Multimedia
[7] Raheja, J. L., Ajay, B., & Chaudhary, A. (2013). Real time
Tools and Applications, 52(1), 147-157.
fabric defect detection system on an embedded DSP
[20] Amet, A. L., Ertuzun, A., & Ercil, A. (1998, April). Texture
platform. Optik-International Journal for Light and Electron
defect detection using subband domain co-occurrence
Optics, 124(21), 5280-5284.
matrices. In Image Analysis and Interpretation, 1998 IEEE
[8] Tsai, D. M., & Chiang, C. H. (2003). Automatic band
Southwest Symposium on (pp. 205-210). IEEE.
selection for wavelet reconstruction in the application of
[21] Saeidi, R. G., Latifi, M., Najar, S. S., & Saeidi, A. G. (2005).
defect detection. Image and Vision Computing, 21(5), 413-
Computer vision-aided fabric inspection system for on-
431.
circular knitting machine. Textile Research Journal, 75(6),
[9] Yang, X., Pang, G., & Yung, N. (2004). Discriminative
492-497.
training approaches to fabric defect classification based on
[22] Shady, E., Gowayed, Y., Abouiiana, M., Youssef, S., &
wavelet transform. Pattern Recognition,37(5), 889-899.
Pastore, C. (2006). Detection and classification of defects in
975

IJRITCC | June 2017, Available @ http://www.ijritcc.org

_______________________________________________________________________________________
 International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
knitted fabric structures. Textile Research Journal, 76(4),
295-300.
[23] 23.. Abou-Taleb, H. A., & Sallam, A. T. M. (2008). On-line
fabric defect detection and full control in a circular knitting
machine. AUTEX Research Journal, 8(1).
[24] Tabassian, M., Ghaderi, R., & Ebrahimpour, R. (2011).
Knitted fabric defect classification for uncertain labels based
on DempsterShafer theory of evidence. Expert Systems with
Applications, 38(5), 5259-5267.
[25] Huang, C. C., & Chen, I. C. (2001). Neural-fuzzy
classification for fabric defects. Textile Research
Journal, 71(3), 220-224.
[26] Zhang, Y., Lu, Z., & Li, J. (2010). Fabric defect
classification using radial basis function network. Pattern
Recognition Letters, 31(13), 2033-2042.
[27] Sezer, O. G., Ertiizun, A., & Eril, A. (2004). Independent
component analysis for texture defect detection. PATTERN
RECOGNITION AND IMAGE ANALYSIS C/C OF
RASPOZNAVANIYE OBRAZOV I ANALIZ
IZOBRAZHENII., 14(2), 303-307.
[28] Kumar, A. (2003). Neural network based detection of local
textile defects.Pattern Recognition, 36(7), 1645-1659.
[29] Kumar, A., & Pang, G. (2000). Fabric defect segmentation
using multichannel blob detectors. Optical
Engineering, 39(12), 3176-3190.
[30] Yildiz, Kazim, Ali Buldu, Mustafa Demetgul, and Zehra
Yildiz. "A novel thermal-based fabric defect detection
technique." The Journal of The Textile Institute 106, no. 3
(2015): 275-283.
[31] 31.. Mak, K. L., Peng, P., & Yiu, K. F. C. (2009). Fabric
defect detection using morphological filters. Image and
Vision Computing, 27(10), 1585-1592.
[32] Raheja, J. L., Kumar, S., & Chaudhary, A. (2013). Fabric
defect detection based on GLCM and Gabor filter: a
comparison. Optik-International Journal for Light and
Electron Optics, 124(23), 6469-6474.
[33] Kumar, A., & Pang, G. K. (2002). Defect detection in
textured materials using optimized filters. Systems, Man, and
Cybernetics, Part B: Cybernetics, IEEE Transactions
on, 32(5), 553-570.
[34] Mak, K. L., Peng, P., & Lau, H. Y. K. (2005, December).
Optimal morphological filter design for fabric defect
detection. In Industrial Technology, 2005. ICIT 2005. IEEE
International Conference on (pp. 799-804). IEEE.
[35] 35.Han, R., & Zhang, L. (2009, May). Fabric defect
detection method based on Gabor filter mask. In Intelligent
Systems, 2009. GCIS'09. WRI Global Congress on (Vol. 3,
pp. 184-188). IEEE.
[36] Zhang, Y., Lu, Z., & Li, J. (2009). Fabric defect detection
and classification using gabor filters and gaussian mixture
model. In Computer VisionACCV 2009 (pp. 635-644).
Springer Berlin Heidelberg.
[37] Jing, J., Zhang, H., Wang, J., Li, P., & Jia, J. (2013). Fabric
defect detection using Gabor filters and defect classification
based on LBP and Tamura method. Journal of The Textile
Institute, 104(1), 18-27
[38] .38. Ngan, H. Y., Pang, G. K., & Yung, N. H. (2010).
Performance evaluation for motif based patterned texture
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
defect detection. Automation Science and Engineering, IEEE
Transactions on, 7(1), 58-72.
[39] Priya, S., Kumar, T. A., & Paul, V. (2011, July). A novel
approach to fabric defect detection using digital image
processing. In Signal Processing, Communication,
Computing and Networking Technologies (ICSCCN), 2011
International Conference on (pp. 228-232). IEEE.
[40] Shu, Y., & Tan, Z. (2004, June). Fabric defects automatic
detection using gabor filters. In Intelligent Control and
Automation, 2004. WCICA 2004. Fifth World Congress
on (Vol. 4, pp. 3378-3380). IEEE.
[41] Yanbei, L., Zhitao, X., Jun, W., & Fang, Z. (2011). Fabric
Defect Detection Method Based on Optimal Gabor Filter
Bank. International Journal of Digital Content Technology
& its Applications, 5(11).
[42] Mallik, B., & Datta, A. K. (1999). Defect detection in fabrics
with a joint transform correlation technique: theoretical basis
and simulation. Textile research journal, 69(11), 829-835.
[43] 43.. Chan, C. H., & Pang, G. K. (2000). Fabric defect
detection by Fourier analysis. Industry Applications, IEEE
Transactions on, 36(5), 1267-1276.
[44] Li, W., Xue, W., & Cheng, L. (2012). Intelligent detection of
defects of yarn-dyed fabrics by energy-based local binary
patterns. Textile Research Journal, 82(19), 1960-1972.
[45] 45.Jasper, W. J., Garnier, S. J., & Potlapalli, H. (1996).
Texture characterization and defect detection using adaptive
wavelets. Optical Engineering, 35(11), 3140-3149
[46] Jasper, W., Joines, J., & Brenzovich, J. (2005). Fabric defect
detection using a genetic algorithm tuned wavelet
filter. Journal of the Textile Institute,96(1), 43-54.
[47] Kim, S., Lee, M. H., & Woo, K. B. (1999). Wavelet analysis
to fabric defects detection in weaving processes. In Industrial
Electronics, 1999. ISIE'99. Proceedings of the IEEE
International Symposium on (Vol. 3, pp. 1406-1409). IEEE.
[48] Schneider, .D., Holtermann, T., Neumann, F., Hehl, A.,
Aach, T., & Gries, T. (2012, July). A vision based system for
high precision online fabric defect detection. In Industrial
Electronics and Applications (ICIEA), 2012 7th IEEE
Conference on (pp. 1494-1499). IEEE.
[49] Tajeripour, F., Kabir, E., & Sheikhi, A. (2007, December).
Defect detection in patterned fabrics using modified local
binary patterns. In Conference on Computational Intelligence
and Multimedia Applications, 2007. International
Conference on (Vol. 2, pp. 261-267). IEEE.
[50] Bu, H. G., Wang, J., & Huang, X. B. (2009). Fabric defect
detection based on multiple fractal features and support
vector data description. Engineering Applications of
Artificial Intelligence, 22(2), 224-235.
[51] 51.Ngan, H. Y., Pang, G. K., & Yung, N. H. (2008). Motif-
based defect detection for patterned fabric. Pattern
Recognition, 41(6), 1878-1894.
[52] Tsai, D. M., & Lin, C. T. (2003). Fast normalized cross
correlation for defect detection. Pattern Recognition
Letters, 24(15), 2625-2631.
[53] Ngan, H. Y., Pang, G. K., & Yung, N. H. (2010). Ellipsoidal
decision regions for motif-based patterned fabric defect
detection. Pattern Recognition, 43(6), 2132-2144.
976
 International Journal on Recent and Innovation Trends in Computing and Communication
Volume: 5 Issue: 6
_______________________________________________________________________________________________
[54] Xue Zhi, Y., Pang, G. K., & Yung, N. H. (2001). Fabric
defect detection using adaptive wavelet. In Acoustics,
Speech, and Signal Processing, 2001.
Proceedings.(ICASSP'01). 2001 IEEE International
Conference on (Vol. 6, pp. 3697-3700). IEEE.
[55] Ngan, H. Y., Pang, G. K., Yung, S. P., & Ng, M. K. (2003,
October). Defect detection on patterned jacquard fabric.
In Applied Imagery Pattern Recognition Workshop, 2003.
Proceedings. 32nd (pp. 163-168). IEEE.
[56] Ngan, H. Y., Pang, G. K., Yung, S. P., & Ng, M. K. (2005).
Wavelet based methods on patterned fabric defect
detection. Pattern recognition, 38(4), 559-576.
[57] Dorrity, J. L., Vachtsevanos, G., & Jasper, W. (1996). Real-
time fabric defect detection and control in weaving
processes. National Textile Center Annual Report, 113-122.
[58] Serdaroglu, A., Ertuzun, A., & Eril, A. (2006). Defect
detection in textile fabric images using wavelet transforms
and independent component analysis. Pattern Recognition
and Image Analysis, 16(1), 61-64.
[59] Wong, W. K., Yuen, C. W. M., Fan, D. D., Chan, L. K., &
Fung, E. H. K. (2009). Stitching defect detection and
classification using wavelet transform and BP neural
network. Expert Systems with Applications, 36(2), 3845-
3856.
[60] Mursalin, T. E., Eishita, F. Z., Islam, A. R., & Alam, M. J.
(2008). Real time automated fabric defect detection system
using microcontroller. Statistics,50, 100.
[61] Roberts, J. W., Elias, J. G., & Jullien, G. A. (1995). U.S.
Patent No. 5,440,648. Washington, DC: U.S. Patent and
Trademark Office.
[62] Dorrity, J. L., & Vachtsevanos, G. (1996, May). On-line
defect detection for weaving systems. In Textile, Fiber and
Film Industry Technical Conference, 1996., IEEE 1996
Annual (pp. 6-pp). IEEE.
[63] Jeong, S. H., Choi, H. T., Kim, S. R., Jaung, J. Y., & Kim, S.
H. (2001). Detecting fabric defects with computer vision and
fuzzy rule generation. Part I: Defect classification by image
processing. Textile Research Journal,71(6), 518-526.
[64] Shumin, D., Zhoufeng, L., & Chunlei, L. (2011, July).
AdaBoost learning for fabric defect detection based on HOG
and SVM. In Multimedia Technology (ICMT), 2011
International Conference on (pp. 2903-2906). IEEE.
[65] Cherkassky, A., & Weinberg, A. (2009). Objective
Evaluation of Textile Fabric Appearance. Part 2: SET Opti-
Grade tester. Grading algorithms, and Testing. Textile
Research Journal.
[66] Kumar, A. (2003). Neural network based detection of local
textile defects.Pattern Recognition, 36(7), 1645-1659.
[67] A. Kumar, Automated inspection of textured web materials
using real Gabor functions, Proc. 2nd SPIE Intl. Conf.
Image & Graphics, ICIG 2002, Hefei (China), pp. 59-62,
Aug. 2002.
[68] A. Kumar and G. Pang, Defect detection in textured
materials using Gabor Filters, IEEE Trans.Ind. Appl., vol.
38, no. 2, pp. 425-440, Mar. 2002.
[69] Bodnarova, Adriana, Mohammed Bennamoun, and Shane
Latham. "Optimal Gabor filters for textile flaw
IJRITCC | June 2017, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
ISSN: 2321-8169
965 977
detection." Pattern recognition 35, no. 12 (2002): 2973-
2991.
[70] Randen, Trygve, and John Hakon Husoy. "Filtering for
texture classification: A comparative study." IEEE
Transactions on pattern analysis and machine
intelligence 21, no. 4 (1999): 291-310.
[71] 71Randen, Trygve, and John H. Husoy. "Multichannel
filtering for image texture segmentation." Optical
Engineering 33, no. 8 (1994): 2617-2625.
[72] Chen, Chien-Chang, and Chaur-Chin Chen. "Filtering
methods for texture discrimination." Pattern Recognition
Letters 20, no. 8 (1999): 783-790.
[73] 73.Vikrant Tiwari,Gaurav Sharma,Automatic Fabric Fault
Detection Using Morphological Operations on Bit
Plane,International Journal of Computer Science and
Network Security,Vol 15.No.10,October 2015.
[74] 74.Priyanka Vyas,Manish Kakhani,Fabric Fault processing
using image processing techniques,International Journal of
Multidisciplinary Research & Development 2015,2(2):29-
31,E-ISSN:2349-4182,P-ISSN:2349-5979.
[75] 75.B.Karuanamoorthy,Dr.D.Somasundareswari,S.P.Sethu,A
utomated Patterned Fabric fault detection using image
processing techniques in Matlab,Volume 4 Issue 1,Jan
2015in International Journal of Advanced Research in
Computer Engineering and Technology(IJARCET).
[76] 76.T.D.Ventakeswaran,G.Arumugam,Defect detection in
fabric images using Singular value decomposition
Technique,International Journal of Computer Technology
and Applications Volume (2),351-356.
[77] 77.Jagruthi Mahure,Y.C.Kulkarni,Fabric faults
processing:Perfections and Imperfections,International
Journal ofComputer Networking,volume 4,Issue 2 ,April
2014.
[78] 78.Ali Rebhi,Sabeur Abid & Farhat Fanaeich,tecture Defect
Detection using Local Homogeneity & Discrete Cosine
Transform ,World Applied Science 31(9):1677-
1683,2014.ISSN:1818-4952.
[79] 79.Vitor Carvalho et.al,Yarn Parameterization of fabrics
prediction using image processing,Textile & Light
Industrial Science & Technology,Vol2 Issue 1,Jan 2013.
[80] 80.Hossein Hasani & Sanaz Behtaz,Measuring the
Roughness of Knitted fabrics by analyzing of surface signals
obtained from image processing,Indian Journal of Fibre and
Textile Research,Volume 38,March 2013,101-105.
[81] 81.Jagruti Mahuri,Y.C.Kulkarni,Fabric fault processing
using image processing technique in Matlab,IJCST,Vol 4
Isssue 2,April June 2013,ISSN:0976-8491.
[82] 82.Jagdesh Lal Raheja,Sunil Kumar,Ankit Chaudary,Fabric
defect detection based on GLCM & Gabor filter A
Comparison,IJLEO-53321,G.Model Elsevier Publication.
[83] 83.Subhassh Roy,Anindita Sengupta,Surajit
Sengupta,Determination of the Diameter spectrogram &
Neps for Yarn Parameterization using image
processing,International Journal of Electrical ,Electronics &
Computer Engineering 2(2),72-76,2013,ISSN:2277-2626.
977